{"id":"297d665c-7e02-4b13-a6ec-d227612858e1","shortId":"ngsexk","kind":"skill","title":"code-review","tagline":"Performs a thorough code review of the current changes or a specified file / pull request. Covers correctness, security, performance, readability, and adherence to project conventions. Outputs prioritised, actionable feedback. TRIGGER when the user writes /code-review or asks for","description":"# Code Review Skill\n\nYou are a senior software engineer performing a rigorous code review. Be direct, constructive, and specific.\n\n## 1. Gather the diff\n\nIf the user has not specified a file or PR, review the current uncommitted or staged changes:\n\n```bash\ngit diff HEAD\n```\n\nIf they pass a file path, read that file. If they pass a PR number or URL, fetch the diff from GitHub.\n\n## 2. Understand the context\n\nBefore commenting, briefly scan:\n\n- The surrounding code and existing tests\n- Any relevant configuration files (`package.json`, `pyproject.toml`, etc.)\n- The project's style guide or linting rules if present\n\n## 3. Review checklist\n\nEvaluate every change against these categories:\n\n### Correctness\n\n- [ ] Logic is correct and handles all expected inputs\n- [ ] Edge cases are considered (empty collections, null/undefined, off-by-one, overflow)\n- [ ] Error paths are handled and errors are not silently swallowed\n- [ ] Concurrency issues absent (race conditions, deadlocks, shared mutable state)\n\n### Security\n\n- [ ] No injection vulnerabilities (SQL, command, XSS, path traversal)\n- [ ] Sensitive data (passwords, tokens, PII) is not logged or exposed\n- [ ] Input is validated and sanitised before use\n- [ ] Dependencies added are not known to be vulnerable\n- [ ] Authentication / authorisation checks are in place where required\n\n### Performance\n\n- [ ] No N+1 queries or unnecessary repeated work in loops\n- [ ] Expensive operations are avoided on hot paths\n- [ ] Memory allocations are reasonable; no obvious leaks\n- [ ] Caching is used where appropriate\n\n### Readability & maintainability\n\n- [ ] Names (variables, functions, types) are clear and consistent\n- [ ] Functions / methods do one thing and are an appropriate length\n- [ ] Complex logic is explained with a comment where warranted\n- [ ] Dead code and commented-out blocks are removed\n- [ ] No magic numbers or hardcoded strings (use constants)\n\n### Tests\n\n- [ ] New behaviour is covered by tests\n- [ ] Edge cases and error paths have test coverage\n- [ ] Tests are readable and do not duplicate production logic\n- [ ] Mocks/stubs are used only where necessary\n\n### Style & conventions\n\n- [ ] Code matches the project's existing style (indentation, quotes, naming)\n- [ ] No lint warnings introduced\n- [ ] Imports are organised correctly\n\n## 4. Output format\n\nProduce the review in this exact structure:\n\n```md\n## Code Review — [file or PR title]\n**Reviewed:** [date]\n**Diff size:** ~[N] lines changed\n\n---\n\n### 🔴 Must Fix (blocks merge)\n- **[File:line]** — [Issue description]\n  > [Suggested fix or example]\n\n### 🟡 Should Fix (important quality issues)\n- **[File:line]** — [Issue description]\n  > [Suggested fix or example]\n\n### 🟢 Suggestions (nice-to-have)\n- **[File:line]** — [Issue description]\n  > [Suggested fix or example]\n\n### ✅ Looks Good\n- [List of things done well]\n\n---\n\n### Summary\n[2-3 sentence overall assessment. State clearly whether this is ready to merge,\nneeds minor changes, or needs significant rework.]\n```\n\n## Rules\n\n- Be specific: always include file name and line number.\n- Show a concrete fix, not just a description of the problem.\n- Do not repeat the same comment for every occurrence — note the pattern once and say \"apply throughout\".\n- Praise genuinely good choices to reinforce good habits.\n- Do not nitpick style issues that are consistent with the rest of the codebase.","tags":["code","review","agent","skills","kambleakash0","agent-skills","ai-agents","ai-assistant","antigravity","automation","claude-code","code-review"],"capabilities":["skill","source-kambleakash0","skill-code-review","topic-agent-skills","topic-ai-agents","topic-ai-assistant","topic-antigravity","topic-automation","topic-claude-code","topic-code-review","topic-codex","topic-cusror","topic-developer-tools","topic-gemini-cli","topic-llm-tools"],"categories":["agent-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/kambleakash0/agent-skills/code-review","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add kambleakash0/agent-skills","source_repo":"https://github.com/kambleakash0/agent-skills","install_from":"skills.sh"}},"qualityScore":"0.453","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 6 github stars · SKILL.md body (3,376 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:14:25.764Z","embedding":null,"createdAt":"2026-05-18T13:22:05.945Z","updatedAt":"2026-05-18T19:14:25.764Z","lastSeenAt":"2026-05-18T19:14:25.764Z","tsv":"'+1':233 '-3':427 '/code-review':38 '1':61 '2':108,426 '3':139 '4':356 'absent':181 'action':31 'ad':215 'adher':25 'alloc':249 'alway':449 'appli':482 'appropri':259,278 'ask':40 'assess':430 'authent':222 'authoris':223 'avoid':244 'bash':82 'behaviour':308 'block':295,382 'briefli':114 'cach':255 'case':158,314 'categori':147 'chang':12,81,144,379,441 'check':224 'checklist':141 'choic':487 'clear':267,432 'code':2,7,42,54,118,290,338,367 'code-review':1 'codebas':505 'collect':162 'command':193 'comment':113,286,293,472 'commented-out':292 'complex':280 'concret':458 'concurr':179 'condit':183 'configur':124 'consid':160 'consist':269,499 'constant':305 'construct':58 'context':111 'convent':28,337 'correct':20,148,151,355 'cover':19,310 'coverag':320 'current':11,77 'data':198 'date':374 'dead':289 'deadlock':184 'depend':214 'descript':387,400,413,463 'diff':64,84,105,375 'direct':57 'done':423 'duplic':327 'edg':157,313 'empti':161 'engin':50 'error':169,174,316 'etc':128 'evalu':142 'everi':143,474 'exact':364 'exampl':391,404,417 'exist':120,343 'expect':155 'expens':241 'explain':283 'expos':206 'feedback':32 'fetch':103 'file':16,72,90,94,125,369,384,397,410,451 'fix':381,389,393,402,415,459 'format':358 'function':264,270 'gather':62 'genuin':485 'git':83 'github':107 'good':419,486,490 'guid':133 'habit':491 'handl':153,172 'hardcod':302 'head':85 'hot':246 'import':352,394 'includ':450 'indent':345 'inject':190 'input':156,207 'introduc':351 'issu':180,386,396,399,412,496 'known':218 'leak':254 'length':279 'line':378,385,398,411,454 'lint':135,349 'list':420 'log':204 'logic':149,281,329 'look':418 'loop':240 'magic':299 'maintain':261 'match':339 'md':366 'memori':248 'merg':383,438 'method':271 'minor':440 'mocks/stubs':330 'must':380 'mutabl':186 'n':232,377 'name':262,347,452 'necessari':335 'need':439,443 'new':307 'nice':407 'nice-to-hav':406 'nitpick':494 'note':476 'null/undefined':163 'number':100,300,455 'obvious':253 'occurr':475 'off-by-on':164 'one':167,273 'oper':242 'organis':354 'output':29,357 'overal':429 'overflow':168 'package.json':126 'pass':88,97 'password':199 'path':91,170,195,247,317 'pattern':478 'perform':4,22,51,230 'pii':201 'place':227 'pr':74,99,371 'prais':484 'present':138 'prioritis':30 'problem':466 'produc':359 'product':328 'project':27,130,341 'pull':17 'pyproject.toml':127 'qualiti':395 'queri':234 'quot':346 'race':182 'read':92 'readabl':23,260,323 'readi':436 'reason':251 'reinforc':489 'relev':123 'remov':297 'repeat':237,469 'request':18 'requir':229 'rest':502 'review':3,8,43,55,75,140,361,368,373 'rework':445 'rigor':53 'rule':136,446 'sanitis':211 'say':481 'scan':115 'secur':21,188 'senior':48 'sensit':197 'sentenc':428 'share':185 'show':456 'signific':444 'silent':177 'size':376 'skill':44 'skill-code-review' 'softwar':49 'source-kambleakash0' 'specif':60,448 'specifi':15,70 'sql':192 'stage':80 'state':187,431 'string':303 'structur':365 'style':132,336,344,495 'suggest':388,401,405,414 'summari':425 'surround':117 'swallow':178 'test':121,306,312,319,321 'thing':274,422 'thorough':6 'throughout':483 'titl':372 'token':200 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-assistant' 'topic-antigravity' 'topic-automation' 'topic-claude-code' 'topic-code-review' 'topic-codex' 'topic-cusror' 'topic-developer-tools' 'topic-gemini-cli' 'topic-llm-tools' 'travers':196 'trigger':33 'type':265 'uncommit':78 'understand':109 'unnecessari':236 'url':102 'use':213,257,304,332 'user':36,67 'valid':209 'variabl':263 'vulner':191,221 'warn':350 'warrant':288 'well':424 'whether':433 'work':238 'write':37 'xss':194","prices":[{"id":"bc726cdc-1332-499c-8d27-b810b0b98809","listingId":"297d665c-7e02-4b13-a6ec-d227612858e1","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"kambleakash0","category":"agent-skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:22:05.945Z"}],"sources":[{"listingId":"297d665c-7e02-4b13-a6ec-d227612858e1","source":"github","sourceId":"kambleakash0/agent-skills/code-review","sourceUrl":"https://github.com/kambleakash0/agent-skills/tree/main/skills/code-review","isPrimary":false,"firstSeenAt":"2026-05-18T13:22:05.945Z","lastSeenAt":"2026-05-18T19:14:25.764Z"}],"details":{"listingId":"297d665c-7e02-4b13-a6ec-d227612858e1","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"kambleakash0","slug":"code-review","github":{"repo":"kambleakash0/agent-skills","stars":6,"topics":["agent-skills","ai-agents","ai-assistant","antigravity","automation","claude-code","code-review","codex","cusror","developer-tools","gemini-cli","llm-tools","mcp","prompt-engineering"],"license":"mit","html_url":"https://github.com/kambleakash0/agent-skills","pushed_at":"2026-05-02T07:18:13Z","description":"A curated collection of custom AgentSkills and token-saving MCP servers for extending the capabilities of AI coding assistants like Claude Code.","skill_md_sha":"85c0e55951b76d54f1dbadca88118fa48d97d9c8","skill_md_path":"skills/code-review/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/kambleakash0/agent-skills/tree/main/skills/code-review"},"layout":"multi","source":"github","category":"agent-skills","frontmatter":{"name":"code-review","description":"Performs a thorough code review of the current changes or a specified file / pull request. Covers correctness, security, performance, readability, and adherence to project conventions. Outputs prioritised, actionable feedback. TRIGGER when the user writes /code-review or asks for a code review, PR review, or feedback on their code."},"skills_sh_url":"https://skills.sh/kambleakash0/agent-skills/code-review"},"updatedAt":"2026-05-18T19:14:25.764Z"}}